Image Denoising With 2D Scale-Mixing Complex Wavelet Transforms

Mammography is routinely used to screen for breast cancer (BC). However, the radiological interpretation of mammogram images is complicated by the heterogeneous nature of normal breast tissue and the fact that cancers are often of the same radiographic density as normal tissue. In this work, we use wavelets to quantify spectral slopes of BC cases and controls and demonstrate their value in classifying images. In addition, we propose asymmetry statistics to be used in forming features which improve the classification result. For the best classification procedure, we achieve approximately 77% accuracy (sensitivity=73%, specificity=84%) in classifying mammograms with and without cancer.

show abstract

“…It is also known as “hyperbolic” [27] and “rectangular” [26]. In its complex version this transform was utilized in [28]. …”

Section: 1 Definition Of Scale-mixing Wavelet Spectramentioning

confidence: 99%

Wavelet-based scaling indices for breast cancer diagnostics

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Coiflets are discrete wavelets with scaling functions that have vanishing moments. All four types of wavelets have been used in biomedical signal and image processing [15][16][17][18][19]. Symlet functions have the disadvantage of generally slower processing than other wavelet-based methods including Daubechies filtering [13][14][15][16][17].…”

Section: Discrete Wavelet Transform To Denoise Temporal Fluorescence mentioning

confidence: 99%

Wavelet analysis of cardiac optical mapping data

Xiong

Nattel

et al. 2015

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…Due to the ill-posed nature of image denoising, it has been widely recognized that the prior knowledge of images plays a key role in enhancing the performance of image denoising methods. A variety of image prior models have been developed, such as transform based [1][2][3], total variation based [4,5], sparse Z. Zha, X. Zhang representation based [6,7] and nonlocal self-similarity based ones [8][9][10]64].…”

Section: Introductionmentioning

confidence: 99%

“…Transform based methods assume that natural images can be sparsely represented by some fixed basis (e.g., wavelet). Motivated by the fact, many wavelet shrinkage based methods have been proposed [1][2][3]. For instance, Chang et al [1] proposed a method called Bayes shrink algorithm to model the wavelet transform coefficients as a generalized Gaussian distribution.…”

Section: Introductionmentioning

confidence: 99%

Group sparsity residual constraint for image denoising with external nonlocal self-similarity prior

et al. 2018

View full text Add to dashboard Cite

Group-based sparse representation has shown great potential in image denoising. However, most existing methods only consider the nonlocal self-similarity (NSS) prior of noisy input image. That is, the similar patches are collected only from degraded input, which makes the quality of image denoising largely depend on the input itself. However, such methods often suffer from a common drawback that the denoising performance may degrade quickly with increasing noise levels. In this paper we propose a new prior model, called group sparsity residual constraint (GSRC). Unlike the conventional group-based sparse representation denoising methods, two kinds of prior, namely, the NSS priors of noisy and pre-filtered images, are used in GSRC. In particular, we integrate these two NSS priors through the mechanism of sparsity residual, and thus, the task of image denoising is converted to the problem of reducing the group sparsity residual. To this end, we first obtain a good estimation of the group sparse coefficients of the original image by pre-filtering, and then the group sparse coefficients of the noisy image are used to approximate this estimation. To improve the accuracy of the nonlocal similar patch selection, an adaptive patch search scheme is designed. Furthermore, to fuse these two NSS prior better, an effective iterative shrinkage algorithm is developed to solve the proposed GSRC model. Experimental results demonstrate that the proposed GSRC modeling outperforms many state-of-the-art denoising methods in terms of the objective and the perceptual metrics.Index Terms-Image denoising, group sparsity residual constraint, nonlocal self-similarity, adaptive patch search, iterative shrinkage algorithm.

show abstract

Image Denoising With 2D Scale-Mixing Complex Wavelet Transforms

Cited by 47 publications

References 27 publications

Wavelet-based scaling indices for breast cancer diagnostics

Wavelet-based scaling indices for breast cancer diagnostics

Wavelet analysis of cardiac optical mapping data

Group sparsity residual constraint for image denoising with external nonlocal self-similarity prior

Contact Info

Product

Resources

About